Literature Review
Overview
Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats.
This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation.
When to Use This Skill
Use this skill when:
- Conducting a systematic literature review for research or publication
- Synthesizing current knowledge on a specific topic across multiple sources
- Performing meta-analysis or scoping reviews
- Writing the literature review section of a research paper or thesis
- Investigating the state of the art in a research domain
- Identifying research gaps and future directions
- Requiring verified citations and professional formatting
Core Workflow
Literature reviews follow a structured, multi-phase workflow:
Phase 1: Planning and Scoping
Define Research Question: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews
- Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"
Establish Scope and Objectives:
- Define clear, specific research questions
- Determine review type (narrative, systematic, scoping, meta-analysis)
- Set boundaries (time period, geographic scope, study types)
Develop Search Strategy:
- Identify 2-4 main concepts from research question
- List synonyms, abbreviations, and related terms for each concept
- Plan Boolean operators (AND, OR, NOT) to combine terms
- Select minimum 3 complementary databases
Set Inclusion/Exclusion Criteria:
- Date range (e.g., last 10 years: 2015-2024)
- Language (typically English, or specify multilingual)
- Publication types (peer-reviewed, preprints, reviews)
- Study designs (RCTs, observational, in vitro, etc.)
- Document all criteria clearly
Phase 2: Systematic Literature Search
Multi-Database Search:
Select databases appropriate for the domain:
Biomedical & Life Sciences:
- Use
gget skill: gget search pubmed "search terms" for PubMed/PMC
- Use
gget skill: gget search biorxiv "search terms" for preprints
- Use
bioservices skill for ChEMBL, KEGG, UniProt, etc.
General Scientific Literature:
- Search arXiv via direct API (preprints in physics, math, CS, q-bio)
- Search Semantic Scholar via API (200M+ papers, cross-disciplinary)
- Use Google Scholar for comprehensive coverage (manual or careful scraping)
Specialized Databases:
- Use
gget alphafold for protein structures
- Use
gget cosmic for cancer genomics
- Use
datacommons-client for demographic/statistical data
- Use specialized databases as appropriate for the domain
Document Search Parameters:
## Search Strategy
### Database: PubMed
- **Date searched**: 2024-10-25
- **Date range**: 2015-01-01 to 2024-10-25
- **Search string**:
("CRISPR"[Title] OR "Cas9"[Title])
AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])
AND 2015:2024[Publication Date]
- **Results**: 247 articles
Repeat for each database searched.
Export and Aggregate Results:
Phase 3: Screening and Selection
Deduplication:
python search_databases.py results.json --deduplicate --output unique_results.json
- Removes duplicates by DOI (primary) or title (fallback)
- Document number of duplicates removed
Title Screening:
- Review all titles against inclusion/exclusion criteria
- Exclude obviously irrelevant studies
- Document number excluded at this stage
Abstract Screening:
- Read abstracts of remaining studies
- Apply inclusion/exclusion criteria rigorously
- Document reasons for exclusion
Full-Text Screening:
- Obtain full texts of remaining studies
- Conduct detailed review against all criteria
- Document specific reasons for exclusion
- Record final number of included studies
Create PRISMA Flow Diagram:
Initial search: n = X
├─ After deduplication: n = Y
├─ After title screening: n = Z
├─ After abstract screening: n = A
└─ Included in review: n = B
Phase 4: Data Extraction and Quality Assessment
Extract Key Data from each included study:
- Study metadata (authors, year, journal, DOI)
- Study design and methods
- Sample size and population characteristics
- Key findings and results
- Limitations noted by authors
- Funding sources and conflicts of interest
Assess Study Quality:
- For RCTs: Use Cochrane Risk of Bias tool
- For observational studies: Use Newcastle-Ottawa Scale
- For systematic reviews: Use AMSTAR 2
- Rate each study: High, Moderate, Low, or Very Low quality
- Consider excluding very low-quality studies
Organize by Themes:
- Identify 3-5 major themes across studies
- Group studies by theme (studies may appear in multiple themes)
- Note patterns, consensus, and controversies
Phase 5: Synthesis and Analysis
Create Review Document from template:
cp assets/review_template.md my_literature_review.md
Write Thematic Synthesis (NOT study-by-study summaries):
- Organize Results section by themes or research questions
- Synthesize findings across multiple studies within each theme
- Compare and contrast different approaches and results
- Identify consensus areas and points of controversy
- Highlight the strongest evidence
Example structure:
#### 3.3.1 Theme: CRISPR Delivery Methods
Multiple delivery approaches have been investigated for therapeutic
gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and
showed high transduction efficiency (65-85%) but raised immunogenicity
concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower
efficiency (40-60%) but improved safety profiles^16-23^.
Critical Analysis:
- Evaluate methodological strengths and limitations across studies
- Assess quality and consistency of evidence
- Identify knowledge gaps and methodological gaps
- Note areas requiring future research
Write Discussion:
- Interpret findings in broader context
- Discuss clinical, practical, or research implications
- Acknowledge limitations of the review itself
- Compare with previous reviews if applicable
- Propose specific future research directions
Phase 6: Citation Verification
CRITICAL: All citations must be verified for accuracy before final submission.
Verify All DOIs:
python scripts/verify_citations.py my_literature_review.md
This script:
- Extracts all DOIs from the document
- Verifies each DOI resolves correctly
- Retrieves metadata from CrossRef
- Generates verification report
- Outputs properly formatted citations
Review Verification Report:
- Check for any failed DOIs
- Verify author names, titles, and publication details match
- Correct any errors in the original document
- Re-run verification until all citations pass
Format Citations Consistently:
- Choose one citation style and use throughout (see
references/citation_styles.md)
- Common styles: APA, Nature, Vancouver, Chicago, IEEE
- Use verification script output to format citations correctly
- Ensure in-text citations match reference list format
Phase 7: Document Generation
Generate PDF:
python scripts/generate_pdf.py my_literature_review.md \
--citation-style apa \
--output my_review.pdf
Options:
--citation-style: apa, nature, chicago, vancouver, ieee
--no-toc: Disable table of contents
--no-numbers: Disable section numbering
--check-deps: Check if pandoc/xelatex are installed
Review Final Output:
- Check PDF formatting and layout
- Verify all sections are present
- Ensure citations render correctly
- Check that figures/tables appear properly
- Verify table of contents is accurate
Quality Checklist:
Database-Specific Search Guidance
PubMed / PubMed Central
Access via gget skill:
# Search PubMed
gget search pubmed "CRISPR gene editing" -l 100
# Search with filters
# Use PubMed Advanced Search Builder to construct complex queries
# Then execute via gget or direct Entrez API
Search tips:
- Use MeSH terms:
"sickle cell disease"[MeSH]
- Field tags:
[Title], [Title/Abstract], [Author]
- Date filters:
2020:2024[Publication Date]
- Boolean operators: AND, OR, NOT
- See MeSH browser: https://meshb.nlm.nih.gov/search
bioRxiv / medRxiv
Access via gget skill:
gget search biorxiv "CRISPR sickle cell" -l 50
Important considerations:
- Preprints are not peer-reviewed
- Verify findings with caution
- Check if preprint has been published (CrossRef)
- Note preprint version and date
arXiv
Access via direct API or WebFetch:
# Example search categories:
# q-bio.QM (Quantitative Methods)
# q-bio.GN (Genomics)
# q-bio.MN (Molecular Networks)
# cs.LG (Machine Learning)
# stat.ML (Machine Learning Statistics)
# Search format: category AND terms
search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""
Semantic Scholar
Access via direct API (requires API key, or use free tier):
- 200M+ papers across all fields
- Excellent for cross-disciplinary searches
- Provides citation graphs and paper recommendations
- Use for finding highly influential papers
Specialized Biomedical Databases
Use appropriate skills:
- ChEMBL:
bioservices skill for chemical bioactivity
- UniProt:
gget or bioservices skill for protein information
- KEGG:
bioservices skill for pathways and genes
- COSMIC:
gget skill for cancer mutations
- AlphaFold:
gget alphafold for protein structures
- PDB:
gget or direct API for experimental structures
Citation Chaining
Expand search via citation networks:
Forward citations (papers citing key papers):
- Use Google Scholar "Cited by"
- Use Semantic Scholar or OpenAlex APIs
- Identifies newer research building on seminal work
Backward citations (references from key papers):
- Extract references from included papers
- Identify highly cited foundational work
- Find papers cited by multiple included studies
Citation Style Guide
Detailed formatting guidelines are in references/citation_styles.md. Quick reference:
APA (7th Edition)
- In-text: (Smith et al., 2023)
- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. Journal, 22(4), 301-318. https://doi.org/10.xxx/yyy
Nature
- In-text: Superscript numbers^1,2^
- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. Nat. Rev. Drug Discov. 22, 301-318 (2023).
Vancouver
- In-text: Superscript numbers^1,2^
- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.
Always verify citations with verify_citations.py before finalizing.
Best Practices
Search Strategy
- Use multiple databases (minimum 3): Ensures comprehensive coverage
- Include preprint servers: Captures latest unpublished findings
- Document everything: Search strings, dates, result counts for reproducibility
- Test and refine: Run pilot searches, review results, adjust search terms
Screening and Selection
- Use clear criteria: Document inclusion/exclusion criteria before screening
- Screen systematically: Title → Abstract → Full text
- Document exclusions: Record reasons for excluding studies
- Consider dual screening: For systematic reviews, have two reviewers screen independently
Synthesis
- Organize thematically: Group by themes, NOT by individual studies
- Synthesize across studies: Compare, contrast, identify patterns
- Be critical: Evaluate quality and consistency of evidence
- Identify gaps: Note what's missing or understudied
Quality and Reproducibility
- Assess study quality: Use appropriate quality assessment tools
- Verify all citations: Run verify_citations.py script
- Document methodology: Provide enough detail for others to reproduce
- Follow guidelines: Use PRISMA for systematic reviews
Writing
- Be objective: Present evidence fairly, acknowledge limitations
- Be systematic: Follow structured template
- Be specific: Include numbers, statistics, effect sizes where available
- Be clear: Use clear headings, logical flow, thematic organization
Common Pitfalls to Avoid
- Single database search: Misses relevant papers; always search multiple databases
- No search documentation: Makes review irreproducible; document all searches
- Study-by-study summary: Lacks synthesis; organize thematically instead
- Unverified citations: Leads to errors; always run verify_citations.py
- Too broad search: Yields thousands of irrelevant results; refine with specific terms
- Too narrow search: Misses relevant papers; include synonyms and related terms
- Ignoring preprints: Misses latest findings; include bioRxiv, medRxiv, arXiv
- No quality assessment: Treats all evidence equally; assess and report quality
- Publication bias: Only positive results published; note potential bias
- Outdated search: Field evolves rapidly; clearly state search date
Example Workflow
Complete workflow for a biomedical literature review:
# 1. Create review document from template
cp assets/review_template.md crispr_sickle_cell_review.md
# 2. Search multiple databases using appropriate skills
# - Use gget skill for PubMed, bioRxiv
# - Use direct API access for arXiv, Semantic Scholar
# - Export results in JSON format
# 3. Aggregate and process results
python scripts/search_databases.py combined_results.json \
--deduplicate \
--rank citations \
--year-start 2015 \
--year-end 2024 \
--format markdown \
--output search_results.md \
--summary
# 4. Screen results and extract data
# - Manually screen titles, abstracts, full texts
# - Extract key data into the review document
# - Organize by themes
# 5. Write the review following template structure
# - Introduction with clear objectives
# - Detailed methodology section
# - Results organized thematically
# - Critical discussion
# - Clear conclusions
# 6. Verify all citations
python scripts/verify_citations.py crispr_sickle_cell_review.md
# Review the citation report
cat crispr_sickle_cell_review_citation_report.json
# Fix any failed citations and re-verify
python scripts/verify_citations.py crispr_sickle_cell_review.md
# 7. Generate professional PDF
python scripts/generate_pdf.py crispr_sickle_cell_review.md \
--citation-style nature \
--output crispr_sickle_cell_review.pdf
# 8. Review final PDF and markdown outputs
Integration with Other Skills
This skill works seamlessly with other scientific skills:
Database Access Skills
- gget: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt
- bioservices: ChEMBL, KEGG, Reactome, UniProt, PubChem
- datacommons-client: Demographics, economics, health statistics
Analysis Skills
- pydeseq2: RNA-seq differential expression (for methods sections)
- scanpy: Single-cell analysis (for methods sections)
- anndata: Single-cell data (for methods sections)
- biopython: Sequence analysis (for background sections)
Visualization Skills
- matplotlib: Generate figures and plots for review
- seaborn: Statistical visualizations
Writing Skills
- brand-guidelines: Apply institutional branding to PDF
- internal-comms: Adapt review for different audiences
Resources
Bundled Resources
Scripts:
scripts/verify_citations.py: Verify DOIs and generate formatted citations
scripts/generate_pdf.py: Convert markdown to professional PDF
scripts/search_databases.py: Process, deduplicate, and format search results
References:
references/citation_styles.md: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)
references/database_strategies.md: Comprehensive database search strategies
Assets:
assets/review_template.md: Complete literature review template with all sections
External Resources
Guidelines:
Tools:
Citation Styles:
Dependencies
Required Python Packages
uv pip install requests # For citation verification
Required System Tools
# For PDF generation
brew install pandoc # macOS
apt-get install pandoc # Linux
# For LaTeX (PDF generation)
brew install --cask mactex # macOS
apt-get install texlive-xetex # Linux
Check dependencies:
python scripts/generate_pdf.py --check-deps
Summary
This literature-review skill provides:
- Systematic methodology following academic best practices
- Multi-database integration via existing scientific skills
- Citation verification ensuring accuracy and credibility
- Professional output in markdown and PDF formats
- Comprehensive guidance covering the entire review process
- Quality assurance with verification and validation tools
- Reproducibility through detailed documentation requirements
Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.
1---2name: "literature-review"3description: "Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature"4metadata:5 source: https://skillmd.com/skills/viggyv/literature-review6---78# Literature Review910## Overview1112Conduct systematic, comprehensive literature reviews following rigorous academic methodology. Search multiple literature databases, synthesize findings thematically, verify all citations for accuracy, and generate professional output documents in markdown and PDF formats.1314This skill integrates with multiple scientific skills for database access (gget, bioservices, datacommons-client) and provides specialized tools for citation verification, result aggregation, and document generation.1516## When to Use This Skill1718Use this skill when:19- Conducting a systematic literature review for research or publication20- Synthesizing current knowledge on a specific topic across multiple sources21- Performing meta-analysis or scoping reviews22- Writing the literature review section of a research paper or thesis23- Investigating the state of the art in a research domain24- Identifying research gaps and future directions25- Requiring verified citations and professional formatting2627## Core Workflow2829Literature reviews follow a structured, multi-phase workflow:3031### Phase 1: Planning and Scoping32331. **Define Research Question**: Use PICO framework (Population, Intervention, Comparison, Outcome) for clinical/biomedical reviews34 - Example: "What is the efficacy of CRISPR-Cas9 (I) for treating sickle cell disease (P) compared to standard care (C)?"35362. **Establish Scope and Objectives**:37 - Define clear, specific research questions38 - Determine review type (narrative, systematic, scoping, meta-analysis)39 - Set boundaries (time period, geographic scope, study types)40413. **Develop Search Strategy**:42 - Identify 2-4 main concepts from research question43 - List synonyms, abbreviations, and related terms for each concept44 - Plan Boolean operators (AND, OR, NOT) to combine terms45 - Select minimum 3 complementary databases46474. **Set Inclusion/Exclusion Criteria**:48 - Date range (e.g., last 10 years: 2015-2024)49 - Language (typically English, or specify multilingual)50 - Publication types (peer-reviewed, preprints, reviews)51 - Study designs (RCTs, observational, in vitro, etc.)52 - Document all criteria clearly5354### Phase 2: Systematic Literature Search55561. **Multi-Database Search**:5758 Select databases appropriate for the domain:5960 **Biomedical & Life Sciences:**61 - Use `gget` skill: `gget search pubmed "search terms"` for PubMed/PMC62 - Use `gget` skill: `gget search biorxiv "search terms"` for preprints63 - Use `bioservices` skill for ChEMBL, KEGG, UniProt, etc.6465 **General Scientific Literature:**66 - Search arXiv via direct API (preprints in physics, math, CS, q-bio)67 - Search Semantic Scholar via API (200M+ papers, cross-disciplinary)68 - Use Google Scholar for comprehensive coverage (manual or careful scraping)6970 **Specialized Databases:**71 - Use `gget alphafold` for protein structures72 - Use `gget cosmic` for cancer genomics73 - Use `datacommons-client` for demographic/statistical data74 - Use specialized databases as appropriate for the domain75762. **Document Search Parameters**:77 ```markdown78 ## Search Strategy7980 ### Database: PubMed81 - **Date searched**: 2024-10-2582 - **Date range**: 2015-01-01 to 2024-10-2583 - **Search string**:84 ```85 ("CRISPR"[Title] OR "Cas9"[Title])86 AND ("sickle cell"[MeSH] OR "SCD"[Title/Abstract])87 AND 2015:2024[Publication Date]88 ```89 - **Results**: 247 articles90 ```9192 Repeat for each database searched.93943. **Export and Aggregate Results**:95 - Export results in JSON format from each database96 - Combine all results into a single file97 - Use `scripts/search_databases.py` for post-processing:98 ```bash99 python search_databases.py combined_results.json \100 --deduplicate \101 --format markdown \102 --output aggregated_results.md103 ```104105### Phase 3: Screening and Selection1061071. **Deduplication**:108 ```bash109 python search_databases.py results.json --deduplicate --output unique_results.json110 ```111 - Removes duplicates by DOI (primary) or title (fallback)112 - Document number of duplicates removed1131142. **Title Screening**:115 - Review all titles against inclusion/exclusion criteria116 - Exclude obviously irrelevant studies117 - Document number excluded at this stage1181193. **Abstract Screening**:120 - Read abstracts of remaining studies121 - Apply inclusion/exclusion criteria rigorously122 - Document reasons for exclusion1231244. **Full-Text Screening**:125 - Obtain full texts of remaining studies126 - Conduct detailed review against all criteria127 - Document specific reasons for exclusion128 - Record final number of included studies1291305. **Create PRISMA Flow Diagram**:131 ```132 Initial search: n = X133 ├─ After deduplication: n = Y134 ├─ After title screening: n = Z135 ├─ After abstract screening: n = A136 └─ Included in review: n = B137 ```138139### Phase 4: Data Extraction and Quality Assessment1401411. **Extract Key Data** from each included study:142 - Study metadata (authors, year, journal, DOI)143 - Study design and methods144 - Sample size and population characteristics145 - Key findings and results146 - Limitations noted by authors147 - Funding sources and conflicts of interest1481492. **Assess Study Quality**:150 - **For RCTs**: Use Cochrane Risk of Bias tool151 - **For observational studies**: Use Newcastle-Ottawa Scale152 - **For systematic reviews**: Use AMSTAR 2153 - Rate each study: High, Moderate, Low, or Very Low quality154 - Consider excluding very low-quality studies1551563. **Organize by Themes**:157 - Identify 3-5 major themes across studies158 - Group studies by theme (studies may appear in multiple themes)159 - Note patterns, consensus, and controversies160161### Phase 5: Synthesis and Analysis1621631. **Create Review Document** from template:164 ```bash165 cp assets/review_template.md my_literature_review.md166 ```1671682. **Write Thematic Synthesis** (NOT study-by-study summaries):169 - Organize Results section by themes or research questions170 - Synthesize findings across multiple studies within each theme171 - Compare and contrast different approaches and results172 - Identify consensus areas and points of controversy173 - Highlight the strongest evidence174175 Example structure:176 ```markdown177 #### 3.3.1 Theme: CRISPR Delivery Methods178179 Multiple delivery approaches have been investigated for therapeutic180 gene editing. Viral vectors (AAV) were used in 15 studies^1-15^ and181 showed high transduction efficiency (65-85%) but raised immunogenicity182 concerns^3,7,12^. In contrast, lipid nanoparticles demonstrated lower183 efficiency (40-60%) but improved safety profiles^16-23^.184 ```1851863. **Critical Analysis**:187 - Evaluate methodological strengths and limitations across studies188 - Assess quality and consistency of evidence189 - Identify knowledge gaps and methodological gaps190 - Note areas requiring future research1911924. **Write Discussion**:193 - Interpret findings in broader context194 - Discuss clinical, practical, or research implications195 - Acknowledge limitations of the review itself196 - Compare with previous reviews if applicable197 - Propose specific future research directions198199### Phase 6: Citation Verification200201**CRITICAL**: All citations must be verified for accuracy before final submission.2022031. **Verify All DOIs**:204 ```bash205 python scripts/verify_citations.py my_literature_review.md206 ```207208 This script:209 - Extracts all DOIs from the document210 - Verifies each DOI resolves correctly211 - Retrieves metadata from CrossRef212 - Generates verification report213 - Outputs properly formatted citations2142152. **Review Verification Report**:216 - Check for any failed DOIs217 - Verify author names, titles, and publication details match218 - Correct any errors in the original document219 - Re-run verification until all citations pass2202213. **Format Citations Consistently**:222 - Choose one citation style and use throughout (see `references/citation_styles.md`)223 - Common styles: APA, Nature, Vancouver, Chicago, IEEE224 - Use verification script output to format citations correctly225 - Ensure in-text citations match reference list format226227### Phase 7: Document Generation2282291. **Generate PDF**:230 ```bash231 python scripts/generate_pdf.py my_literature_review.md \232 --citation-style apa \233 --output my_review.pdf234 ```235236 Options:237 - `--citation-style`: apa, nature, chicago, vancouver, ieee238 - `--no-toc`: Disable table of contents239 - `--no-numbers`: Disable section numbering240 - `--check-deps`: Check if pandoc/xelatex are installed2412422. **Review Final Output**:243 - Check PDF formatting and layout244 - Verify all sections are present245 - Ensure citations render correctly246 - Check that figures/tables appear properly247 - Verify table of contents is accurate2482493. **Quality Checklist**:250 - [ ] All DOIs verified with verify_citations.py251 - [ ] Citations formatted consistently252 - [ ] PRISMA flow diagram included (for systematic reviews)253 - [ ] Search methodology fully documented254 - [ ] Inclusion/exclusion criteria clearly stated255 - [ ] Results organized thematically (not study-by-study)256 - [ ] Quality assessment completed257 - [ ] Limitations acknowledged258 - [ ] References complete and accurate259 - [ ] PDF generates without errors260261## Database-Specific Search Guidance262263### PubMed / PubMed Central264265Access via `gget` skill:266```bash267# Search PubMed268gget search pubmed "CRISPR gene editing" -l 100269270# Search with filters271# Use PubMed Advanced Search Builder to construct complex queries272# Then execute via gget or direct Entrez API273```274275**Search tips**:276- Use MeSH terms: `"sickle cell disease"[MeSH]`277- Field tags: `[Title]`, `[Title/Abstract]`, `[Author]`278- Date filters: `2020:2024[Publication Date]`279- Boolean operators: AND, OR, NOT280- See MeSH browser: https://meshb.nlm.nih.gov/search281282### bioRxiv / medRxiv283284Access via `gget` skill:285```bash286gget search biorxiv "CRISPR sickle cell" -l 50287```288289**Important considerations**:290- Preprints are not peer-reviewed291- Verify findings with caution292- Check if preprint has been published (CrossRef)293- Note preprint version and date294295### arXiv296297Access via direct API or WebFetch:298```python299# Example search categories:300# q-bio.QM (Quantitative Methods)301# q-bio.GN (Genomics)302# q-bio.MN (Molecular Networks)303# cs.LG (Machine Learning)304# stat.ML (Machine Learning Statistics)305306# Search format: category AND terms307search_query = "cat:q-bio.QM AND ti:\"single cell sequencing\""308```309310### Semantic Scholar311312Access via direct API (requires API key, or use free tier):313- 200M+ papers across all fields314- Excellent for cross-disciplinary searches315- Provides citation graphs and paper recommendations316- Use for finding highly influential papers317318### Specialized Biomedical Databases319320Use appropriate skills:321- **ChEMBL**: `bioservices` skill for chemical bioactivity322- **UniProt**: `gget` or `bioservices` skill for protein information323- **KEGG**: `bioservices` skill for pathways and genes324- **COSMIC**: `gget` skill for cancer mutations325- **AlphaFold**: `gget alphafold` for protein structures326- **PDB**: `gget` or direct API for experimental structures327328### Citation Chaining329330Expand search via citation networks:3313321. **Forward citations** (papers citing key papers):333 - Use Google Scholar "Cited by"334 - Use Semantic Scholar or OpenAlex APIs335 - Identifies newer research building on seminal work3363372. **Backward citations** (references from key papers):338 - Extract references from included papers339 - Identify highly cited foundational work340 - Find papers cited by multiple included studies341342## Citation Style Guide343344Detailed formatting guidelines are in `references/citation_styles.md`. Quick reference:345346### APA (7th Edition)347- In-text: (Smith et al., 2023)348- Reference: Smith, J. D., Johnson, M. L., & Williams, K. R. (2023). Title. *Journal*, *22*(4), 301-318. https://doi.org/10.xxx/yyy349350### Nature351- In-text: Superscript numbers^1,2^352- Reference: Smith, J. D., Johnson, M. L. & Williams, K. R. Title. *Nat. Rev. Drug Discov.* **22**, 301-318 (2023).353354### Vancouver355- In-text: Superscript numbers^1,2^356- Reference: Smith JD, Johnson ML, Williams KR. Title. Nat Rev Drug Discov. 2023;22(4):301-18.357358**Always verify citations** with verify_citations.py before finalizing.359360## Best Practices361362### Search Strategy3631. **Use multiple databases** (minimum 3): Ensures comprehensive coverage3642. **Include preprint servers**: Captures latest unpublished findings3653. **Document everything**: Search strings, dates, result counts for reproducibility3664. **Test and refine**: Run pilot searches, review results, adjust search terms367368### Screening and Selection3691. **Use clear criteria**: Document inclusion/exclusion criteria before screening3702. **Screen systematically**: Title → Abstract → Full text3713. **Document exclusions**: Record reasons for excluding studies3724. **Consider dual screening**: For systematic reviews, have two reviewers screen independently373374### Synthesis3751. **Organize thematically**: Group by themes, NOT by individual studies3762. **Synthesize across studies**: Compare, contrast, identify patterns3773. **Be critical**: Evaluate quality and consistency of evidence3784. **Identify gaps**: Note what's missing or understudied379380### Quality and Reproducibility3811. **Assess study quality**: Use appropriate quality assessment tools3822. **Verify all citations**: Run verify_citations.py script3833. **Document methodology**: Provide enough detail for others to reproduce3844. **Follow guidelines**: Use PRISMA for systematic reviews385386### Writing3871. **Be objective**: Present evidence fairly, acknowledge limitations3882. **Be systematic**: Follow structured template3893. **Be specific**: Include numbers, statistics, effect sizes where available3904. **Be clear**: Use clear headings, logical flow, thematic organization391392## Common Pitfalls to Avoid3933941. **Single database search**: Misses relevant papers; always search multiple databases3952. **No search documentation**: Makes review irreproducible; document all searches3963. **Study-by-study summary**: Lacks synthesis; organize thematically instead3974. **Unverified citations**: Leads to errors; always run verify_citations.py3985. **Too broad search**: Yields thousands of irrelevant results; refine with specific terms3996. **Too narrow search**: Misses relevant papers; include synonyms and related terms4007. **Ignoring preprints**: Misses latest findings; include bioRxiv, medRxiv, arXiv4018. **No quality assessment**: Treats all evidence equally; assess and report quality4029. **Publication bias**: Only positive results published; note potential bias40310. **Outdated search**: Field evolves rapidly; clearly state search date404405## Example Workflow406407Complete workflow for a biomedical literature review:408409```bash410# 1. Create review document from template411cp assets/review_template.md crispr_sickle_cell_review.md412413# 2. Search multiple databases using appropriate skills414# - Use gget skill for PubMed, bioRxiv415# - Use direct API access for arXiv, Semantic Scholar416# - Export results in JSON format417418# 3. Aggregate and process results419python scripts/search_databases.py combined_results.json \420 --deduplicate \421 --rank citations \422 --year-start 2015 \423 --year-end 2024 \424 --format markdown \425 --output search_results.md \426 --summary427428# 4. Screen results and extract data429# - Manually screen titles, abstracts, full texts430# - Extract key data into the review document431# - Organize by themes432433# 5. Write the review following template structure434# - Introduction with clear objectives435# - Detailed methodology section436# - Results organized thematically437# - Critical discussion438# - Clear conclusions439440# 6. Verify all citations441python scripts/verify_citations.py crispr_sickle_cell_review.md442443# Review the citation report444cat crispr_sickle_cell_review_citation_report.json445446# Fix any failed citations and re-verify447python scripts/verify_citations.py crispr_sickle_cell_review.md448449# 7. Generate professional PDF450python scripts/generate_pdf.py crispr_sickle_cell_review.md \451 --citation-style nature \452 --output crispr_sickle_cell_review.pdf453454# 8. Review final PDF and markdown outputs455```456457## Integration with Other Skills458459This skill works seamlessly with other scientific skills:460461### Database Access Skills462- **gget**: PubMed, bioRxiv, COSMIC, AlphaFold, Ensembl, UniProt463- **bioservices**: ChEMBL, KEGG, Reactome, UniProt, PubChem464- **datacommons-client**: Demographics, economics, health statistics465466### Analysis Skills467- **pydeseq2**: RNA-seq differential expression (for methods sections)468- **scanpy**: Single-cell analysis (for methods sections)469- **anndata**: Single-cell data (for methods sections)470- **biopython**: Sequence analysis (for background sections)471472### Visualization Skills473- **matplotlib**: Generate figures and plots for review474- **seaborn**: Statistical visualizations475476### Writing Skills477- **brand-guidelines**: Apply institutional branding to PDF478- **internal-comms**: Adapt review for different audiences479480## Resources481482### Bundled Resources483484**Scripts:**485- `scripts/verify_citations.py`: Verify DOIs and generate formatted citations486- `scripts/generate_pdf.py`: Convert markdown to professional PDF487- `scripts/search_databases.py`: Process, deduplicate, and format search results488489**References:**490- `references/citation_styles.md`: Detailed citation formatting guide (APA, Nature, Vancouver, Chicago, IEEE)491- `references/database_strategies.md`: Comprehensive database search strategies492493**Assets:**494- `assets/review_template.md`: Complete literature review template with all sections495496### External Resources497498**Guidelines:**499- PRISMA (Systematic Reviews): http://www.prisma-statement.org/500- Cochrane Handbook: https://training.cochrane.org/handbook501- AMSTAR 2 (Review Quality): https://amstar.ca/502503**Tools:**504- MeSH Browser: https://meshb.nlm.nih.gov/search505- PubMed Advanced Search: https://pubmed.ncbi.nlm.nih.gov/advanced/506- Boolean Search Guide: https://www.ncbi.nlm.nih.gov/books/NBK3827/507508**Citation Styles:**509- APA Style: https://apastyle.apa.org/510- Nature Portfolio: https://www.nature.com/nature-portfolio/editorial-policies/reporting-standards511- NLM/Vancouver: https://www.nlm.nih.gov/bsd/uniform_requirements.html512513## Dependencies514515### Required Python Packages516```bash517uv pip install requests # For citation verification518```519520### Required System Tools521```bash522# For PDF generation523brew install pandoc # macOS524apt-get install pandoc # Linux525526# For LaTeX (PDF generation)527brew install --cask mactex # macOS528apt-get install texlive-xetex # Linux529```530531Check dependencies:532```bash533python scripts/generate_pdf.py --check-deps534```535536## Summary537538This literature-review skill provides:5395401. **Systematic methodology** following academic best practices5412. **Multi-database integration** via existing scientific skills5423. **Citation verification** ensuring accuracy and credibility5434. **Professional output** in markdown and PDF formats5445. **Comprehensive guidance** covering the entire review process5456. **Quality assurance** with verification and validation tools5467. **Reproducibility** through detailed documentation requirements547548Conduct thorough, rigorous literature reviews that meet academic standards and provide comprehensive synthesis of current knowledge in any domain.